Research Presentations and Invited Talks
This page highlights my recent research presentations, invited talks, and conference appearances. Each entry includes relevant materials and information about the presentation content.
Predicting High-Risk Behaviors in Individuals with Profound Autism Using Sleep and Other Environmental Factors
Abstract
This presentation explores the relationship between sleep architecture and daytime behaviors in individuals with profound autism spectrum disorder. Using a novel privacy-preserving sensing approach combined with machine learning techniques, we demonstrate how disruptions in sleep patterns can predict challenging behaviors in the following 24-hour period. The talk presents a framework for early intervention that could significantly improve quality of life and reduce caregiver burden for families supporting individuals with profound autism.
Key Topics
- Novel off-body sensing technologies for sleep monitoring
- Machine learning approaches for behavioral prediction
- Privacy-preserving edge computing in vulnerable populations
- Practical intervention strategies based on predictive modeling
- Clinical implications and future directions for personalized care
Can Sleep Architecture and Behavior Patterns Predict Next-Day Challenging Behavior in Autism?
Abstract
This presentation discusses our ongoing research into the relationship between sleep quality and challenging behaviors in children with autism spectrum disorder. The talk highlights our novel methodological approach using non-intrusive sensing technology and privacy-preserving edge computing to monitor sleep patterns without disrupting the home environment. We present preliminary findings from our collaboration with The Center for Discovery, demonstrating how specific sleep architecture disruptions may serve as predictive biomarkers for next-day behavioral challenges, offering potential pathways for early intervention.
Key Points
- Development and validation of off-body sleep monitoring systems
- Privacy-preserving computation approaches for vulnerable populations
- Correlation between specific sleep parameters and behavioral outcomes
- Application of machine learning for behavioral prediction
- Implementation challenges in real-world settings
- Translation into clinical practice and personalized intervention strategies
Acknowledgments
This research is supported by the Thrasher Research Fund Early Career Award and conducted in collaboration with The Center for Discovery.
Advancing Neurological Care Through Novel Sensing Pipelines for Detection and Intervention
Abstract
This presentation provides an overview of my research program focused on developing novel sensing technologies and AI-driven analytics for neurological and developmental disorders. I discuss our multi-modal approach to biomarker discovery that combines wearable sensors, environmental monitoring, and privacy-preserving edge computing to identify early indicators of cognitive decline and behavioral challenges. The talk emphasizes the translation of these technologies into practical clinical applications that can improve patient outcomes through early detection and personalized intervention strategies.
Research Areas Highlighted
- In-ear EEG and multimodal sensing for cognitive impairment detection
- Privacy-preserving computing architectures for vulnerable populations
- Explainable AI approaches for clinical decision support
- Implementation challenges and solutions in real-world healthcare settings
- Ethical considerations in AI-driven healthcare technologies
Future Directions
The presentation concludes with a discussion of future research directions, including the development of closed-loop intervention systems that can adapt to individual patient needs in real-time, expansion of sensing modalities, and broader applications across different neurological conditions.